We have developed a system that combines IE techniques. In particular, we have proposed two different approximations for the extraction of DDIs from texts. The first approximation proposes a hybrid approach, which combines shallow parsing and pattern matching to extract relations between drugs from biomedical texts. A pharmacist defined a set of lexical patterns (12) to capture the various language constructions used to express DDIs in pharmacological texts. The second approximation is based on a supervised machine learning approach, in particular, a kernel-based approach that uses Support Vector Machines (SVM). While the first approximation based on pattern matching achieves low performance (Precision=48.7%, Recall=25.7%, F-measure=33.6%), the approach based on kernel-methods achieves better performance, especially better recall (Precision=55.1%, Recall=82.3%, F-measure=66.0%). A web tool can be found at http://163.117.129.57:8080/ddiextractorweb).

Búsqueda de documentos en la colección MedLine 2010 y procesamiento de textos para el reconocimiento de fármacos y sus interacciones.

DrugDDIExtractor combines several IE techniques (described in the previous paragraph) and has been implemented using Java. The web tool is written in JSP. Also, this tool integrates Apache Lucene for supportin the search of documents from Medline 2010 collection.

This is the first system to extract drug names and drug-drug interactions from biomedical texts.

This system was part of the thesis “Application of information extraction techniques to pharmacological domain: extracting drug-drug interactions” Isabel Segura-Bedmar, Advisor: Paloma Martínez. Recently, this thesis has been granted with the Extraordinary PhD award 2011. This work has been partially supported by the Spanish research projects: MA2VICMR consortium (S2009/TIC-1542, www.mavir.net), a network of excellence funded by the Madrid Regional Government and TIN2007-67407-C03-01 (BRAVO: Advanced Multimodal and Multilingual Question Answering).

• Isabel Segura-Bedmar, Paloma Martínez, César de Pablo-Sánchez, (2011). A linguistic rule-based approach to extract drug-drug interactions from pharmacological documents, January, 2011, BMC BioInformatics, ISSN: 1471-2105, Volumen: In Press.
• Isabel Segura-Bedmar, Paloma Martínez, César de Pablo-Sánchez, (2010). Extracting drug-drug interactions from biomedical texts., May, 2010, BMC BioInformatics, ISSN: 1471-2105, Volumen: 11, Número: Suppl 5.
• Isabel Segura-Bedmar, Paloma Martínez, César de Pablo-Sánchez, (2010). Combining syntactic information and domain-specific lexical patterns to extract Drug-Drug Interactions from biomedical texts., Toronto, Canada, October, 2010, ACM Fourth International Workshop on Data and Text Mining in Bioinformatics (DTMBIO 10)., ACM.
• Isabel Segura-Bedmar, Paloma Martínez, María Segura-Bedmar, (2008). Drug Name Recognition and classification in biomedical texts. , September, 2008, Drug Discovery Today, Elsevier Science, ISSN: 1359-6446, Volumen: 13, Número: 17-18, Páginas: 816-823, url.